文献速递呼吸衰竭与机械通气重症综合管理与镇静镇痛

COVID-19高流量鼻导管失败预测模型的种族差异

Racial Differences in Accuracy of Predictive Models for High-Flow Nasal Cannula Failure in COVID-19.
PubMed 文献 · Crit Care Explor · 2024-03-12
一句话结论XGB模型预测COVID-19高流量鼻导管失败的区分度优于ROX指数(AUROC 0.707比0.616),但黑人患者中准确性显著低于白人患者。

该回顾性队列研究纳入2020年3月至2022年4月四家埃默里大学医院收治的984例入住ICU 24小时内接受高流量鼻导管(HFNC)治疗的成人COVID-19患者,开发四种监督机器学习模型预测HFNC失败(启动后7天内插管或死亡),并与ROX指数比较,按自报种族评估模型准确性。前60%(n=594)用于训练、后40%(n=390)用于验证。317例(32.2%)发生HFNC失败。XGB模型AUROC最高(0.707),是唯一显著优于ROX指数(AUROC 0.616)的模型。XGB模型在黑人患者中AUROC 0.663,显著低于白人患者的0.808(p=0.02);当仅限动脉血气数据完整的患者、或改为预测死亡而非复合结局时,种族差异减小且不再有统计学意义。作者结论:XGB模型区分度优于ROX指数,但预测准确性存在种族差异,需进一步研究以理解和减轻临床机器学习模型中的潜在偏倚来源并提高其公平性。

要点

  • 984例COVID-19接受HFNC的成人中317例(32.2%)在启动后7天内插管或死亡(HFNC失败)。
  • XGB模型预测HFNC失败的AUROC为0.707,是唯一显著优于ROX指数(AUROC 0.616)的模型。
  • XGB模型在黑人患者中AUROC 0.663,显著低于白人患者的0.808(p=0.02)。
  • 限动脉血气数据完整的患者或改预测死亡而非复合结局时,XGB模型种族差异减小且不再有统计学意义。
  • 作者结论:XGB模型区分度优于ROX指数,但存在种族准确性差异,需进一步研究以理解和减轻临床机器学习模型的潜在偏倚来源并提高其公平性。

适用人群与场景

  • 2020年3月至2022年4月入住四家埃默里大学医院、入住ICU 24小时内接受HFNC治疗的成人COVID-19患者984例,前60%(n=594)训练、后40%(n=390)验证。

诊断标准与关键阈值

  • HFNC失败定义为HFNC启动后7天内插管或死亡。

研究设计与关键结果

  • 回顾性队列研究,984例成人COVID-19患者中317例(32.2%)发生HFNC失败。
  • 四种监督机器学习模型用入住ICU前24小时常规临床变量预测HFNC失败;XGB模型AUROC最高(0.707),是唯一显著优于ROX指数(AUROC 0.616)的模型。
  • XGB模型在黑人患者中AUROC 0.663,显著低于白人患者的0.808(p=0.02)。
  • 限动脉血气数据完整的患者、或XGB模型改为预测死亡(而非可能受插管临床决策偏倚影响的复合失败结局)时,种族差异减小且不再有统计学意义。

证据类型、等级与局限

  • 证据类型:回顾性队列研究。
  • 局限:预测HFNC失败的复合结局可能受插管临床决策偏倚影响;作者指出需进一步研究以理解和减轻临床机器学习模型中的潜在偏倚来源并提高其公平性。

对床旁实践的改变

  • 作者认为XGB模型对COVID-19 HFNC失败的区分度优于ROX指数,但存在种族准确性差异;需进一步研究以理解和减轻临床机器学习模型的潜在偏倚来源并提高其公平性。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

OBJECTIVES: To develop and validate machine learning (ML) models to predict high-flow nasal cannula (HFNC) failure in COVID-19, compare their performance to the respiratory rate-oxygenation (ROX) index, and evaluate model accuracy by self-reported race.

DESIGN: Retrospective cohort study.

SETTING: Four Emory University Hospitals in Atlanta, GA.

PATIENTS: Adult patients hospitalized with COVID-19 between March 2020 and April 2022 who received HFNC therapy within 24 hours of ICU admission were included.

INTERVENTIONS: None.

MEASUREMENTS AND MAIN RESULTS: Four types of supervised ML models were developed for predicting HFNC failure (defined as intubation or death within 7 d of HFNC initiation), using routine clinical variables from the first 24 hours of ICU admission. Models were trained on the first 60% (n = 594) of admissions and validated on the latter 40% (n = 390) of admissions to simulate prospective implementation. Among 984 patients included, 317 patients (32.2%) developed HFNC failure. eXtreme Gradient Boosting (XGB) model had the highest area under the receiver-operator characteristic curve (AUROC) for predicting HFNC failure (0.707), and was the only model with significantly better performance than the ROX index (AUROC 0.616). XGB model had significantly worse performance in Black patients compared with White patients (AUROC 0.663 vs. 0.808, p = 0.02). Racial differences in the XGB model were reduced and no longer statistically significant when restricted to patients with nonmissing arterial blood gas data, and when XGB model was developed to predict mortality (rather than the composite outcome of failure, which could be influenced by biased clinical decisions for intubation).

CONCLUSIONS: Our XGB model had better discrimination for predicting HFNC failure in COVID-19 than the ROX index, but had racial differences in accuracy of predictions. Further studies are needed to understand and mitigate potential sources of biases in clinical ML models and to improve their equitability.

来源:Crit Care Explor,查看原文。版权归原作者所有。

参考来源

  1. Yang P, Gregory IA, Robichaux C, et al. Racial Differences in Accuracy of Predictive Models for High-Flow Nasal Cannula Failure in COVID-19. Crit Care Explor. 2024. PMID: 38975567. doi:10.1097/CCE.0000000000001059

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。